Software Engineer – RL Environments

Headcount: 3

Job Details

• Experience: 1–4 years
• Salary: Not specified
• Equity: Competitive equity
• Visa sponsorship: H-1B, O-1, OPT
• Employment type: Full-time
• Work type: In person

Benefits & Perks

• Medical, vision, and dental insurance
• 401(k) with employer match
• Daily meal stipend
• Monthly wellness stipend
• Direct impact on frontier AI model development
• Work with leading AI labs

About This Role

As a Software Engineer (Environments), you will design datasets and evaluation rubrics that directly influence how frontier models learn. You’ll work hands-on with research teams at AI labs, experimenting with data-collection strategies, diagnosing model failure modes, and developing metrics to determine whether a model is improving. You’ll move quickly from hypothesis to live experiment, and your work will feed directly into model training runs at scale.

Day to day, you will design data slices that expose meaningful failure modes across domains such as finance, code, and enterprise workflows. You will build and refine reward signals for RLHF and RLVR pipelines, develop quantitative frameworks for measuring dataset quality, diversity, and downstream impact on alignment and capability, and partner with lab research teams to translate training objectives into concrete data and evaluation specifications.

What You’ll Do

• Design data slices and explore data shapes that expose meaningful model failure modes across domains such as finance, code, and enterprise workflows
• Build and refine evaluation rubrics and reward signals for RLHF and RLVR training pipelines
• Model annotator behavior and run experiments to improve model capabilities
• Develop quantitative frameworks for measuring dataset quality, diversity, and downstream impact on model alignment and capability
• Create and manage real-world and synthetic data pipelines
• Partner with lab research teams to translate training objectives into concrete data and evaluation specifications

Requirements

• Strong Python skills and experience building reliable data pipelines, experimentation infrastructure, or evaluation systems
• Hands-on experience with LLM evaluations, post-training, reward modeling, RLHF/RLVR, or closely related ML infrastructure
• Strong experimental judgment, including the ability to form hypotheses, define metrics, design controlled experiments, and interpret noisy results
• Experience creating or evaluating datasets, including measuring quality, diversity, coverage, and downstream model performance
• Comfort reasoning across unfamiliar domains such as software engineering, finance, policy, and enterprise workflows, and learning them quickly
• A bias toward building over theorizing